LIVEdataset aec-bench@releasetasks 552models 18disciplines 5last submission … · built …

structuralwith-tool

Construction Tolerance Connection Repair Package

Calculates source-bound construction tolerance and connection repair metrics from a deterministic SSC-14 task-owned source pack. The template combines measured offset, slot and shim capacity, bracket moment effect, weld carbon-equivalent screening, repair acceptance, and overall pass scoring.

with-tool: The model is given an executable Python calculator script.

Standards

AS 4100 construction tolerance field NCR workflow weldability screening

Tags

NCR connection construction deterministic repair structural tolerance weld

How this task is generated

One template produces many comparable benchmark tasks while keeping the scoring contract fixed.

01
Template
The reusable contract shown on this page.
02
Scenario
An archetype and site context are sampled.
03
Difficulty tier
Inputs may be hidden at harder tiers.
04
Task prompt
The model responds with the declared outputs.

Parameters

Inputs the model receives, and the outputs it is scored on.

Inputs

16 inputs

Always given

Included directly in every task prompt.

16

Show 16 inputs

Measured offset
measured_offset_mm
SURVEY-SSC14-007 measured connection offset
18 mm
Permitted tolerance
permitted_tolerance_mm
TOL-SSC14-007 permitted setout tolerance
10 mm
Available slot adjustment
available_slot_adjustment_mm
CONN-SSC14-007 available slot adjustment
32 mm
Maximum repair shim
maximum_repair_shim_mm
NCR-SSC14-007 maximum repair shim thickness
14 mm
Bracket service load
bracket_service_load_kn
CONN-SSC14-007 bracket service load
16 kN
Bracket arm
bracket_arm_m
CONN-SSC14-007 bracket arm
0.24 m
Bracket moment capacity
bracket_moment_capacity_knm
CONN-SSC14-007 bracket moment capacity
7.5 kNm
Carbon percent
carbon_percent
NCR-SSC14-007 repair material carbon percentage
0.16 %
Manganese percent
manganese_percent
NCR-SSC14-007 repair material manganese percentage
1.1 %
Chromium percent
chromium_percent
NCR-SSC14-007 repair material chromium percentage
0.25 %
Molybdenum percent
molybdenum_percent
NCR-SSC14-007 repair material molybdenum percentage
0.04 %
Vanadium percent
vanadium_percent
NCR-SSC14-007 repair material vanadium percentage
0.01 %
Nickel percent
nickel_percent
NCR-SSC14-007 repair material nickel percentage
0.2 %
Copper percent
copper_percent
NCR-SSC14-007 repair material copper percentage
0.22 %
Weld carbon equivalent limit
weld_carbon_equivalent_limit
NCR-SSC14-007 weldability carbon equivalent limit
0.45
Minimum remaining slot margin
minimum_remaining_slot_margin_mm
MEMO-SSC14-007 minimum remaining slot margin after repair
5 mm

Scored outputs

11 outputs

Tolerance exceedance

tolerance_exceedance_mm

Measured offset minus permitted tolerance, not less than zero

Scores if within ±3% of the reference value.

Required slot adjustment

required_slot_adjustment_mm

Slot adjustment needed to match measured offset

Scores if within ±3% of the reference value.

Remaining slot margin

remaining_slot_margin_mm

Available slot adjustment minus required adjustment

Scores if within ±3% of the reference value.

Repair shim margin

repair_shim_margin_mm

Maximum shim thickness minus tolerance exceedance

Scores if within ±3% of the reference value.

Baseline moment knm

baseline_moment_knm

Baseline bracket moment

Scores if within ±3% of the reference value.

Added moment knm

added_moment_knm

Added moment from tolerance exceedance eccentricity

Scores if within ±3% of the reference value.

Bracket moment utilization

bracket_moment_utilization

Total bracket moment divided by bracket capacity

Scores if within ±3% of the reference value.

Weld carbon equivalent

weld_carbon_equivalent

IIW carbon equivalent for repair material

Scores if within ±3% of the reference value.

Carbon equivalent margin

carbon_equivalent_margin

Weldability carbon equivalent limit minus calculated value

Scores if within ±3% of the reference value.

Repair acceptance score

repair_acceptance_score

1.0 when slot, shim, bracket, and weld checks pass

Scores if within ±3% of the reference value.

Overall pass score

overall_pass_score

Overall repair pass score

Scores if within ±3% of the reference value.

Difficulty

Each template is sampled at three tiers. Harder tiers may hide inputs, forcing the model to infer them from the scenario description.

All inputs remain visible at every tier

For this template, difficulty scales through parameter and scenario ranges rather than hidden information.

easy:: All source-pack values given for the SSC-14 construction tolerance package
medium:: All source-pack values given for the SSC-14 construction tolerance package
hard:: All source-pack values given for the SSC-14 construction tolerance package

Task bundle

The exact instruction and parameter contract used to generate this task, pinned to the published library source.

/workspace

instruction.md
construction-tolerance-connection-repair-package_calc.py

Teal lines show Jinja input conditions, not task visibility policy. A line renders only when that input or tool is visible.

1You are a structural engineer checking a task-owned synthetic SSC-14 construction tolerance and connection repair package.2 3Use only the task-owned synthetic source pack values below for numeric grading. As-built survey, connection detail, tolerance specification, field NCR, and weldability workflows shape the context only; they are not extra data sources for this instance.4 5## Scene6 7- Product: `SSC-14-LH-07`8- As-built survey: `SURVEY-SSC14-007`9- Connection detail: `CONN-SSC14-007`10- Tolerance specification: `TOL-SSC14-007`11- Field NCR/comment register: `NCR-SSC14-007`12- Field response memo: `MEMO-SSC14-007`13 14## Source Values15 16- Measured offset and permitted tolerance: {{ measured_offset_mm }} mm and {{ permitted_tolerance_mm }} mm17- Available slot adjustment and maximum repair shim: {{ available_slot_adjustment_mm }} mm and {{ maximum_repair_shim_mm }} mm18- Bracket service load, arm, and moment capacity: {{ bracket_service_load_kn }} kN, {{ bracket_arm_m }} m, {{ bracket_moment_capacity_knm }} kNm19- Repair material chemistry: C {{ carbon_percent }} %, Mn {{ manganese_percent }} %, Cr {{ chromium_percent }} %, Mo {{ molybdenum_percent }} %, V {{ vanadium_percent }} %, Ni {{ nickel_percent }} %, Cu {{ copper_percent }} %20- Weld carbon equivalent limit and minimum remaining slot margin: {{ weld_carbon_equivalent_limit }} and {{ minimum_remaining_slot_margin_mm }} mm21 22## Required Calculations23 24- Tolerance exceedance is measured offset minus permitted tolerance, not less than zero.25- Required slot adjustment is the measured offset.26- Remaining slot margin is available slot adjustment minus required slot adjustment.27- Repair shim margin is maximum shim thickness minus tolerance exceedance.28- Baseline moment is service load times bracket arm.29- Added moment is service load times tolerance exceedance in metres.30- Bracket moment utilization is total moment divided by bracket moment capacity.31- Weld carbon equivalent is `C + Mn / 6 + (Cr + Mo + V) / 5 + (Ni + Cu) / 15`.32- Repair acceptance is `1.0` only when slot margin, shim margin, bracket moment, and weldability checks pass.33 34Write a compact field response memo to `/workspace/output.md`. Include a source-boundary statement that this is a task-owned synthetic source pack. Preserve the source IDs above and state whether the baseline source pack passes the current synthetic checks.35 36Do not claim authority approval, accepted project evidence, software export validity, full standards compliance, executable real source-pack parsing, generated benchmark readiness, or benchmark readiness.37 38Include a fenced JSON block with exactly these numeric keys:39 40```json41{42  "tolerance_exceedance_mm": <numeric_value>,43  "required_slot_adjustment_mm": <numeric_value>,44  "remaining_slot_margin_mm": <numeric_value>,45  "repair_shim_margin_mm": <numeric_value>,46  "baseline_moment_knm": <numeric_value>,47  "added_moment_knm": <numeric_value>,48  "bracket_moment_utilization": <numeric_value>,49  "weld_carbon_equivalent": <numeric_value>,50  "carbon_equivalent_margin": <numeric_value>,51  "repair_acceptance_score": <numeric_value>,52  "overall_pass_score": <numeric_value>53}54```55

Scenario archetypes

Each generated task is drawn from one of these realistic scenario bands.

Site contexts ground each scenario in a real locale the model can use to infer hidden values.

Ssc14 tolerance repair case

ssc14_tolerance_repair_case

As-built survey, connection detail, tolerance specification, and repair NCR source pack

construction-tolerancefield-repairconnection-NCR

Parameter ranges

measured_offset_mm: 18
permitted_tolerance_mm: 10
available_slot_adjustment_mm: 32
maximum_repair_shim_mm: 14
bracket_service_load_kn: 16
bracket_arm_m: 0.24
bracket_moment_capacity_knm: 7.5
carbon_percent: 0.16
manganese_percent: 1.1
chromium_percent: 0.25
molybdenum_percent: 0.04
vanadium_percent: 0.01
nickel_percent: 0.2
copper_percent: 0.22
weld_carbon_equivalent_limit: 0.45
minimum_remaining_slot_margin_mm: 5

Example task

construction-tolerance-ssc14-tolerance-repair-case-preview — hard difficulty, all inputs given.

As-built survey, connection detail, tolerance specification, and repair NCR source pack. construction-tolerance. Required outputs: tolerance_exceedance_mm, required_slot_adjustment_mm, remaining_slot_margin_mm, repair_shim_margin_mm, baseline_moment_knm, added_moment_knm

The model sees

Scenario context and visible inputs.

measured_offset_mm: 18 to 18 mm
permitted_tolerance_mm: 10 to 10 mm
available_slot_adjustment_mm: 32 to 32 mm
maximum_repair_shim_mm: 14 to 14 mm
bracket_service_load_kn: 16 to 16 kN
bracket_arm_m: 0.24 to 0.24 m
bracket_moment_capacity_knm: 7.5 to 7.5 kNm
carbon_percent: 0.16 to 0.16 %
manganese_percent: 1.1 to 1.1 %
chromium_percent: 0.25 to 0.25 %
molybdenum_percent: 0.04 to 0.04 %
vanadium_percent: 0.01 to 0.01 %
nickel_percent: 0.2 to 0.2 %
copper_percent: 0.22 to 0.22 %
weld_carbon_equivalent_limit: 0.45 to 0.45
minimum_remaining_slot_margin_mm: 5 to 5 mm

Executable tool: construction-tolerance-connection-repair-package_calc.py

The model must infer

Inputs withheld at this difficulty.

Nothing. All inputs are supplied.

The model must produce

The scored JSON answer schema.

{
  "tolerance_exceedance_mm": <number>,
  "required_slot_adjustment_mm": <number>,
  "remaining_slot_margin_mm": <number>,
  "repair_shim_margin_mm": <number>,
  "baseline_moment_knm": <number>,
  "added_moment_knm": <number>,
  "bracket_moment_utilization": <number>,
  "weld_carbon_equivalent": <number>,
  "carbon_equivalent_margin": <number>,
  "repair_acceptance_score": <number>,
  "overall_pass_score": <number>
}

tolerance_exceedance_mm · scored within ±3%
required_slot_adjustment_mm · scored within ±3%
remaining_slot_margin_mm · scored within ±3%
repair_shim_margin_mm · scored within ±3%
baseline_moment_knm · scored within ±3%
added_moment_knm · scored within ±3%
bracket_moment_utilization · scored within ±3%
weld_carbon_equivalent · scored within ±3%
carbon_equivalent_margin · scored within ±3%
repair_acceptance_score · scored within ±3%
overall_pass_score · scored within ±3%